| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.885931558935361, | |
| "eval_steps": 500, | |
| "global_step": 650, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.604562737642586, | |
| "grad_norm": 0.9130080342292786, | |
| "learning_rate": 1.153846153846154e-05, | |
| "loss": 2.7233, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.604562737642586, | |
| "eval_accuracy": 0.36823535797644247, | |
| "eval_loss": 3.186351776123047, | |
| "eval_runtime": 1.7733, | |
| "eval_samples_per_second": 10.151, | |
| "eval_steps_per_second": 1.692, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.885931558935361, | |
| "step": 650, | |
| "total_flos": 5425467752448000.0, | |
| "train_loss": 2.6658438814603365, | |
| "train_runtime": 1438.1403, | |
| "train_samples_per_second": 3.651, | |
| "train_steps_per_second": 0.452 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 650, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5425467752448000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |